{"id":"W2027399021","doi":"10.1177/0265532207076363","title":"The challenges of the Ontario Secondary School Literacy Test for second language students","year":2007,"lang":"en","type":"article","venue":"Language Testing","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Literacy; Test (biology); Psychology; Mathematics education; Vocabulary; Context (archaeology); Reading (process); English as a second language; Language proficiency; Language assessment; Pedagogy; Linguistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001527666,0.0001972514,0.0002089431,0.00007172694,0.00036965,0.00008999265,0.0006713927,0.0001099033,0.00968408],"category_scores_gemma":[0.001711345,0.0001270248,0.0001367495,0.0001998077,0.00008539326,0.0001019499,0.0001373759,0.0006059461,0.0000649857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008002898,"about_ca_system_score_gemma":0.00007224191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001972474,"about_ca_topic_score_gemma":0.0104911,"domain_scores_codex":[0.9983564,0.0001147018,0.0004515934,0.0003185431,0.0002505334,0.0005082351],"domain_scores_gemma":[0.9956551,0.003123608,0.0003273544,0.0006830052,0.0001126306,0.00009833123],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.000167446,0.0004094151,0.1368472,0.0001930498,0.0002900216,0.0003029247,0.4866394,0.000003225331,0.02598303,0.001457716,0.002375237,0.3453313],"study_design_scores_gemma":[0.001756078,0.0001974341,0.8851979,0.0001678875,0.00004955269,0.0001045111,0.09748836,0.000009586689,0.002934234,0.00009413287,0.01169293,0.000307444],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9249005,0.01903411,0.00004053805,0.0001493482,0.0005367137,0.0004682063,0.00002331365,0.00009866417,0.05474858],"genre_scores_gemma":[0.9743323,8.785945e-7,0.0007906856,0.002058849,0.0004704866,0.00004068418,0.000009012924,0.00004261497,0.02225452],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7483506,"threshold_uncertainty_score":0.9912212,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02266960080524535,"score_gpt":0.3419876094318603,"score_spread":0.319318008626615,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}